# AI use cases for GPT Researcher (assafelovic/gpt-researcher)

Repo: [assafelovic/gpt-researcher](https://github.com/assafelovic/gpt-researcher) | Use cases: 3 | Page: https://dedupedai.com/use-cases/assafelovic-gpt-researcher/

GPT Researcher is an autonomous agent that conducts deep research on any topic with any LLM provider and writes a cited report. It runs as a web app, a pip package, a Docker stack or a Claude skill, can research your local documents, and can mix web search with MCP data sources such as GitHub.

This file holds every use case of this repo. Each one starts with a "## " heading and ends with its URL.

- Run a deep research web app on your machine: https://dedupedai.com/use-cases/assafelovic-gpt-researcher/run-a-deep-research-web-app-with-gpt-researcher/
- Write a report from your own documents: https://dedupedai.com/use-cases/assafelovic-gpt-researcher/research-your-own-documents-with-gpt-researcher/
- Combine web search with GitHub data via MCP: https://dedupedai.com/use-cases/assafelovic-gpt-researcher/combine-web-and-github-mcp-research-with-gpt-researcher/

## How to run a deep research web app on your machine with GPT Researcher

Repo: [assafelovic/gpt-researcher](https://github.com/assafelovic/gpt-researcher) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README

Clone the project, set your keys and start the local server to get research reports from a browser UI.

**Who it is for:** Anyone who wants a research report on a topic in minutes.

**The problem:** Reading dozens of sources by hand for one question takes hours.

**The outcome:** A local web app at localhost:8000 that writes research reports.

### Steps

1. Clone with `git clone https://github.com/assafelovic/gpt-researcher.git` and `cd gpt-researcher`
2. Set your OPENAI_API_KEY and TAVILY_API_KEY as environment variables or in a .env file
3. Install and start with `pip install -r requirements.txt` and `python -m uvicorn main:app --reload`
4. Open http://localhost:8000 and enter your research question

### Prompt to paste into your agent

```text
Set up assafelovic/gpt-researcher locally: clone it, install with `pip install -r requirements.txt`, start it with `python -m uvicorn main:app --reload`, and run a report on <my topic>.
```

### Caveat

Reports summarize web sources automatically, so verify key claims against the cited sources before relying on them.

Risk, cost: Each report makes many LLM and search API calls billed to your OpenAI and Tavily accounts.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/assafelovic-gpt-researcher/run-a-deep-research-web-app-with-gpt-researcher/

## How to write a report from your own documents with GPT Researcher

Repo: [assafelovic/gpt-researcher](https://github.com/assafelovic/gpt-researcher) | Difficulty: Beginner | Time: 30 minutes | Basis: From the README

Point GPT Researcher at a folder of PDFs, Word, Excel, PowerPoint, CSV or Markdown files and research them instead of the web.

**Who it is for:** A consultant or team with a pile of internal documents.

**The problem:** Internal reports are scattered across files nobody has time to read end to end.

**The outcome:** A research report grounded in your local documents.

### Steps

1. Install the app as in the README Installation steps, or the package with `pip install gpt-researcher`
2. Point it at your folder with `export DOC_PATH="./my-docs"`
3. In the web app, choose My Documents from the Report Source dropdown
4. With the pip package, pass report_source as local when creating GPTResearcher

### Prompt to paste into your agent

```text
Using assafelovic/gpt-researcher, set `export DOC_PATH="./my-docs"` to <my folder> and produce a report on <question> using report_source local.
```

### Caveat

Supported formats per the README are PDF, plain text, CSV, Excel, Markdown, PowerPoint and Word.

Risk, privacy: Your document contents are sent to the configured LLM provider; use a local OpenAI-compatible endpoint via OPENAI_BASE_URL if they are confidential.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/assafelovic-gpt-researcher/research-your-own-documents-with-gpt-researcher/

## How to combine web search with GitHub data via MCP with GPT Researcher

Repo: [assafelovic/gpt-researcher](https://github.com/assafelovic/gpt-researcher) | Difficulty: Intermediate | Time: 45 minutes | Basis: From the README

Use the pip package with the MCP retriever so research pulls from the web and from an MCP server like GitHub in one run.

**Who it is for:** A developer researching open source projects or code ecosystems.

**The problem:** Web search alone misses repository details that live behind an API.

**The outcome:** A report that blends web results with data from an MCP data source.

### Steps

1. Install the package with `pip install gpt-researcher`
2. Enable hybrid research with `export RETRIEVER=tavily,mcp`
3. Create GPTResearcher with mcp_configs for the GitHub server, using npx with @modelcontextprotocol/server-github and your GITHUB_TOKEN
4. Await conduct_research and then write_report

### Prompt to paste into your agent

```text
With assafelovic/gpt-researcher, run `pip install gpt-researcher`, set `export RETRIEVER=tavily,mcp`, and write a script using mcp_configs for the GitHub MCP server to research <my question about repos>.
```

### Caveat

The README also offers a Claude skill install with `npx skills add assafelovic/gpt-researcher`.

Risk, credentials: The GitHub MCP server uses your GITHUB_TOKEN; give it a read-only token scoped to what the research needs.

Disclaimer: Third-party repos we don't own or vouch for. AI-generated use cases can be wrong: review everything and run at your own risk. Full text: https://dedupedai.com/disclaimer/

URL: https://dedupedai.com/use-cases/assafelovic-gpt-researcher/combine-web-and-github-mcp-research-with-gpt-researcher/